© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221280
    Prev
    Next
    INDEX
    Explanations

    scheduled servicing

    np_acts-logits-general · gemini-2.5-flash-lite

    invented, formulated, improved, craft, measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ऱ
    0.49
    वेळी
    0.49
    ర్మ
    0.45
    띠
    0.44
    小朋友
    0.44
    드릴
    0.43
    就算是
    0.43
    诚信
    0.43
    嘉宾
    0.43
    چار
    0.43
    POSITIVE LOGITS
     entered
    0.48
     jaz
    0.48
     measurements
    0.48
    𝘯
    0.48
     conditioners
    0.48
    ेश्व
    0.47
    questao
    0.47
     invented
    0.46
     disks
    0.46
     formulations
    0.46
    Activations Density 0.000%

    No Known Activations